IMAGE CLASSIFICATION DEVICE AND IMAGE CLASSIFICATION PROGRAM

• US 20110103700A1
• Filed: 12/01/2008
• Published: 05/05/2011
• Est. Priority Date: 12/03/2007
• Status: Active Grant

• Current Assignee: National University Corporation Hokkaido University
• Original Assignee: National University Corporation Hokkaido University
• Inventors: Haseyama, Miki
• Granted Patent: US 8,180,161 B2
• Time in Patent Office: Days
• US Class Current: 382/225
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/54 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06T 1/00 General purpose image data processing
• CPC Class Codes: G06T 7/44 using image operators, e.g. filters, edge density metrics or local histograms
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 10/762 using clustering, e.g. of similar faces in social networks
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59

Abstract

An image classification device includes a characteristic value set calculation unit 11 that calculates a characteristic value set of the whole image for each of multiple sets of image data in an image database 51, detects an edge of the set of the image data, and calculates a characteristic value set of the detected edge portions; a first clustering unit 12 that classifies the multiple sets of image data into multiple clusters on the basis of the characteristic value sets of the whole images; a second clustering unit 13 that further classifies the multiple clusters classified by the first clustering unit 12 into multiple clusters on the basis of the characteristic value sets of the edge portions; and a cluster integration unit 14 that determines which pixels constitutes a subject in each of the multiple sets of image data, based on the composition of the image, and integrates some of the multiple clusters classified by the second clustering unit 13 together based on the pixels constituting the subject.

Claims

1. An image classification device for classifying sets of image data into groups of similar images, comprising:

an image database for storage of the sets of image data;

a characteristic value set calculation unit configured to calculate a characteristic value set of the whole image of the set of image data, detect an edge of the corresponding set of image data, and calculate a characteristic value set of the detected edge portion, for each of the sets of image data;

a first clustering unit that configured to classify the sets of image data into clusters based on the characteristic value sets of the whole images;

a second clustering unit configured to further classify the clusters classified by the first clustering unit into clusters based on the characteristic value sets of the edge portions;

a cluster integration unit configured to determine which pixels constitutes a subject in each of the sets of image data, based on a composition of the corresponding image, and integrate some of the clusters classified by the second clustering unit together based on the pixels constituting the subject; and

a display unit configured to arbitrarily arrange thumbnails of the sets of image data, update and display coordinates of each of the thumbnails based on the characteristic value set of the whole image of the image data, the characteristic value set of the edge portion of the image data, the characteristic value set of the pixels constitution the subject of the image data, and the clusters of the image data determined by the cluster integration unit, calculate a shift amount of each of the thumbnails, and repeat the processing of updating and displaying the coordinates until the shift amount of each of the thumbnails is converged to 0.

2. (canceled)

3. (canceled)

4. (canceled)

5. (canceled)

6. (canceled)

7. (canceled)

8. (canceled)

9. (canceled)

10. (canceled)

11. An image classification program for classifying sets

of image data into groups of similar images, allowing a computer to function as:

characteristic value set calculation means for calculating a characteristic value set of the whole image of set of image data stored in an image database, detecting an edge of the corresponding set of the image data, and calculating a characteristic value set of the detected edge portion, for each of the sets of image data;

first clustering means for classifying the sets of image data into clusters based on the characteristic value sets of the whole images;

second clustering means for further classifying the clusters classified by the first clustering means into clusters based on the characteristic value sets of the edge portions;

cluster integration means for determining which pixels constitutes a subject in each of the sets of image data, based on a composition of the image, and integrates some of the clusters classified by the second clustering means together based on the pixels constituting the subject; and

display means for arbitrarily arranging thumbnails of the sets of image data, updating and displaying coordinates of each of the thumbnails based on the characteristic value set of the whole image of the image data, the characteristic value set of the edge portion of the image data, the characteristic value set of the pixels constituting the subject of the image data, calculating a shift amount of each of the thumbnails, and repeating the processing of updating and displaying the coordinates until the shift amount of each of the thumbnails is converged to 0.

12. (canceled)

13. (canceled)

14. (canceled)

15. (canceled)

16. (canceled)

17. (canceled)

18. (canceled)

19. (canceled)

20. (canceled)